Merve Ceyhan

Merve Ceyhan

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 June 2023 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
MCMerve Ceyhan
Merve Ceyhan
YKYusuf Kartal
Yusuf Kartal
KÖKemal Özkan
Kemal Özkan
ESErol Seke
Erol Seke

30 April 2021 in Eskişehir Osmangazi Üniversitesi Mühendislik ve Mimarlık Fakültesi Dergisi
Verified
Journal Article
Closed access
MCMerve Ceyhan
Merve Ceyhan
EYEsra N. Yolacan
Esra N. Yolacan
İnternet kullanımının artması ve teknolojik gelişmelerle beraber insanlar her gün yüzlerce fotoğraf çekmektedir. Gün geçtikçe artan fotoğraflar telefon hafızasında fazlasıyla yer kaplamaktadır. Flash disk, bilgisayar ve telefonlarda bu fotoğrafların saklanması, kaybolma ve bozulma gibi durumlar nedeniyle çok güvenilir olmamaktadır. Bu durum telefon dışında yeni depolama alanları ihtiyacını ortaya çıkarmıştır. Bu noktada alternatif olarak bulut depolama sistemleri kullanılmaktadır. Bulut depolama alanları sisteme erişim ve saldırılara karşı güvenlik tedbirleri içermektedir fakat sisteme yüklenen resimler üzerinde doğrudan bir işlem yapmamaktadır. Bulut hesaplar bazen kötü niyetli kişiler tarafından ele geçirilmekte ve kişilerin fotoğrafları çalınabilmektedir. Bu durumu önlemek için depolama işleminden önce görüntü üzerinde şifreleme algoritmaları kullanan bir sistem önerilmiştir. Sistemde CodeIgniter (PHP Framework) altındaki çeşitli simetrik şifreleme algoritmaları karşılaştırılarak incelenmiş ve uygulama sonuçları sunulmuştur. Görüntülerin şifrelenerek farklı bir dosya uzantısı ile bulut depolama(AWS) ortamında ya da lokal ortamda saklanması sağlanmıştır. Bu çalışmada önerilen sistem ile görüntülerin tutuldukları ortamdan bağımsız olarak daha güvenli bir depolama imkanı sağlanması hedeflenmiştir.


10 April 2026 in Neural Computing and Applications
Verified
Journal Article
Open access
PDF file
MCMerve Ceyhan
Merve Ceyhan
UGUğur Gürel
Uğur Gürel
Cancer classification is one of the important fields of study that plays a critical role in determining accurate diagnosis and effective treatment strategies. This work introduces a hybrid ensemble learning method using radiomics features. It combines machine learning and deep learning methodologies for better classification of lung cancer types and includes explainable AI. The proposed method aims to achieve higher classification performance by combining the strengths of deep learning and machine learning models. Classification performance is increased by combining machine learning algorithms such as Random Forest, Gradient Boosting, Extreme Gradient Boosting, Light Gradient Boosting Machine, Support Vector Machine, and TabNet model as a deep learning model in a hybrid structure. In addition, PNG conversion from DICOM images, extraction of radiomic features from the image, and optimization steps with Optuna are also included. In this study, where three different types of lung cancer were classified as Adenocarcinoma, Small Cell Carcinoma and Squamous Cell Carcinoma, 99% accuracy rate was achieved by using the voting classifier method. Experimental studies show that the proposed hybrid ensemble learning method provides higher accuracy, sensitivity, and specificity than traditional machine learning models and other ensemble approaches. These results reveal that the hybrid ensemble learning approach offers significant potential as an innovative method in cancer classification. The usability of the developed model in medical applications and its applicability to real-world problems will be evaluated in more detail in further studies. This study aims to establish a basis for developing more reliable and practical solutions in the field of cancer classification.

21 October 2025
Verified
Book Chapter
Closed access
PDF file
NANihat Adar
Nihat Adar
KAKaan Algür
Kaan Algür
SBSinem Bozkurt
Sinem Bozkurt
MCMerve Ceyhan
Merve Ceyhan

11 August 2025
Verified
Thesis
Closed access
MCMerve Ceyhan
Merve Ceyhan
Within the scope of the thesis study, the reflectance values of 24 different wheat species were measured using the Near-Infrared (NIR) Spectrometer device and used as input parameters in machine learning and deep learning approaches to classify wheat species. These approaches were compared with each other, and the results were evaluated. As a result of the approaches discussed, it has been seen that machine learning techniques do not show sufficient performance to distinguish between reflectance value and species. When classification is made with the deep learning model, higher accuracy values have been achieved than machine learning algorithms. The deep learning approach has been handled separately to classify with direct reflectance data and classify images created from reflectance data.